© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38657
    Prev
    Next
    INDEX
    Explanations

    fewer, cheaper, easier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IRIS
    0.46
    ANDS
    0.45
     বজ্র
    0.44
    orifice
    0.44
    Vis
    0.43
     Noct
    0.41
    Ъ
    0.41
    厄
    0.41
     Народ
    0.41
    aż
    0.40
    POSITIVE LOGITS
     playgrounds
    0.55
     cheaper
    0.54
     fewer
    0.50
     laboratories
    0.47
     Fewer
    0.47
     labs
    0.46
     lures
    0.45
     পারে
    0.45
     lego
    0.45
     easier
    0.45
    Activations Density 0.007%

    No Known Activations